Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only readOnlyHint=false, the description carries most of the behavioral load and does note that a recorded decision cannot later be changed by the agent ('Only RepuTend can change a recorded decision') and that an appeal's outcome is recorded here as the next decision, which is valuable non-obvious context. It stops short of saying what state the case transitions to or what happens if the tool is called twice on a decided case (error vs overwrite).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action and the value mapping are front-loaded, and each sentence addresses a distinct failure mode (no decision yet, deleted review, ambiguous match, duplicate recording, appeal path). It is dense and somewhat parenthetical-heavy, so an agent must parse carefully, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter mutation with no output schema, this covers everything an agent needs: what to record, what not to record, how to disambiguate the case, the irreversibility of the write, and how later decisions arrive. The only omission is error/second-call behavior, which is minor here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for `decision` by spelling out both enum values' real-world meaning. `case_id` is only indirectly explained (it must be one of 'your filed cases', discoverable via list_disputable_reviews/get_case) with no format or sourcing detail beyond that inference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Record Trustpilot's decision on one of your filed cases') and immediately maps the two enum values to the human-readable outcomes the agent sees in Trustpilot's UI (removed_by_tp = Removed, retained = Kept online). It is clearly separable from siblings like record_appeal, mark_filed and get_case, which are referenced only as downstream or lookup steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use rules and, more importantly, explicit when-NOT rules: 'Investigating is no decision yet, so record nothing' and 'A review gone from your profile is not a decision either.' It also prescribes a fallback procedure (match quoted review words via list_disputable_reviews then get_case) and an ambiguity rule (ask the user if more than one case could match), plus a once-only constraint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.